Wavelet Transform and its Application in the Analysis of Economic and Financial Time Series

The thesis deals with a brief compilation of the theory of Fourier transform, linear filtration and a triad of wavelet transforms -- the maximal overlap discrete wavelet transform (MODWT), the discrete wavelet transform (DWT) and the continuous wavelet transform (CWT). These transforms are among others applied to the analysis of the time-varying character of variability in the time series, to the detection of events of significant changes of variability, to the removal of noise in the time series (denoising) and to the time-scale analysis of the relationship of two time series. The analyzed time series used in this thesis are the logarithm of the Garman-Klass estimate of the historical volatility, the time series of stock returns and the logarithm of the monthly inflation rate. In some cases artificial time series are analyzed. The procedures and methods introduced in the thesis might be well implemented in the analysis of other economic and financial time series. The contribution of the thesis is a brief and easy-to-use compilation of the wavelet theory and the application of the wavelet transform to such financial and economic time series, where such an analysis tool has never been applied before. New insights into the properties of time series are thus obtained, insights, which might be hardly recovered by traditional means and methods.